Search Results for author: Ding-Jie Chen

Found 11 papers, 3 papers with code

From Graph Local Embedding to Deep Metric Learning

no code implementations29 Sep 2021 Bing-Jhang Lin, Ding-Jie Chen, He-Yen Hsieh, Tyng-Luh Liu

We comprehensively identify the missing neighborhood relationships issue of conventional embedding and propose a novel approach, termed as Graph Local Embedding (GLE), to deep metric learning.

Metric Learning Retrieval

Adaptive Image Transformer for One-Shot Object Detection

no code implementations CVPR 2021 Ding-Jie Chen, He-Yen Hsieh, Tyng-Luh Liu

One-shot object detection tackles a challenging task that aims at identifying within a target image all object instances of the same class, implied by a query image patch.

Object object-detection +2

Natural World Distribution via Adaptive Confusion Energy Regularization

no code implementations1 Jan 2021 Yen-Chi Hsu, Cheng-Yao Hong, Wan-Cyuan Fan, Ding-Jie Chen, Ming-Sui Lee, Davi Geiger, Tyng-Luh Liu

The Fine-Grained Visual Classification (FGVC) problem is notably characterized by two intriguing properties, significant inter-class similarity and intra-class variations, which cause learning an effective FGVC classifier a challenging task.

Fine-Grained Image Classification

Feature Integration and Group Transformers for Action Proposal Generation

no code implementations1 Jan 2021 He-Yen Hsieh, Ding-Jie Chen, Tung-Ying Lee, Tyng-Luh Liu

The task of temporal action proposal generation (TAPG) aims to provide high-quality video segments, i. e., proposals that potentially contain action events.

Temporal Action Proposal Generation

See-Through-Text Grouping for Referring Image Segmentation

no code implementations ICCV 2019 Ding-Jie Chen, Songhao Jia, Yi-Chen Lo, Hwann-Tzong Chen, Tyng-Luh Liu

With the refined heatmap, we update the textual representation of the referring expression by re-evaluating its attention distribution and then compute a new STEP heatmap as the next input to the ConvRNN.

Image Segmentation object-detection +6

Instance-Level Meta Normalization

1 code implementation CVPR 2019 Songhao Jia, Ding-Jie Chen, Hwann-Tzong Chen

This paper presents a normalization mechanism called Instance-Level Meta Normalization (ILM~Norm) to address a learning-to-normalize problem.

SwipeCut: Interactive Segmentation with Diversified Seed Proposals

no code implementations18 Dec 2018 Ding-Jie Chen, Hwann-Tzong Chen, Long-Wen Chang

At each round of interaction the user is only presented with a small number of informative query seeds that are far apart from each other.

Image Segmentation Interactive Segmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.